metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- conll2003
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: distilbert-base-uncased-finetuned-ner
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: conll2003
type: conll2003
args: conll2003
metrics:
- name: Precision
type: precision
value: 0.9263064854712186
- name: Recall
type: recall
value: 0.9379125181787672
- name: F1
type: f1
value: 0.9320733740967203
- name: Accuracy
type: accuracy
value: 0.9838117781625813
distilbert-base-uncased-finetuned-ner
This model is a fine-tuned version of distilbert-base-uncased on the conll2003 dataset. It achieves the following results on the evaluation set:
- Loss: 0.0614
- Precision: 0.9263
- Recall: 0.9379
- F1: 0.9321
- Accuracy: 0.9838
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.2418 | 1.0 | 878 | 0.0709 | 0.9168 | 0.9242 | 0.9204 | 0.9806 |
| 0.0514 | 2.0 | 1756 | 0.0622 | 0.9175 | 0.9338 | 0.9255 | 0.9826 |
| 0.0306 | 3.0 | 2634 | 0.0614 | 0.9263 | 0.9379 | 0.9321 | 0.9838 |
Framework versions
- Transformers 4.19.3
- Pytorch 1.11.0+cu113
- Datasets 2.2.2
- Tokenizers 0.12.1